The patch titled
Subject: mm, THP, swap: support PMD swap mapping in split_swap_cluster()
has been added to the -mm tree. Its filename is
mm-thp-swap-support-pmd-swap-mapping-in-split_swap_cluster.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-thp-swap-support-pmd-swap-mapping-in-split_swap_cluster.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-thp-swap-support-pmd-swap-mapping-in-split_swap_cluster.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Huang Ying <ying.huang@xxxxxxxxx>
Subject: mm, THP, swap: support PMD swap mapping in split_swap_cluster()
When splitting a THP in swap cache or failing to allocate a THP when
swapin a huge swap cluster, the huge swap cluster will be split. In
addition to clear the huge flag of the swap cluster, the PMD swap mapping
count recorded in cluster_count() will be set to 0. But we will not touch
PMD swap mappings themselves, because it is hard to find them all
sometimes. When the PMD swap mappings are operated later, it will be
found that the huge swap cluster has been split and the PMD swap mappings
will be split at that time.
Unless splitting a THP in swap cache (specified via "force" parameter),
split_swap_cluster() will return -EEXIST if there is SWAP_HAS_CACHE flag
in swap_map[offset]. Because this indicates there is a THP corresponds to
this huge swap cluster, and it isn't desired to split the THP.
When splitting a THP in swap cache, the position to call
split_swap_cluster() is changed to before unlocking sub-pages. So that
all sub-pages will be kept locked from the THP has been split to the huge
swap cluster is split. This makes the code much easier to be reasoned.
Link: http://lkml.kernel.org/r/20180622035151.6676-8-ying.huang@xxxxxxxxx
Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Shaohua Li <shli@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Zi Yan <zi.yan@xxxxxxxxxxxxxx>
Cc: Daniel Jordan <daniel.m.jordan@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
diff -puN include/linux/swap.h~mm-thp-swap-support-pmd-swap-mapping-in-split_swap_cluster include/linux/swap.h
--- a/include/linux/swap.h~mm-thp-swap-support-pmd-swap-mapping-in-split_swap_cluster
+++ a/include/linux/swap.h
@@ -617,10 +617,10 @@ static inline swp_entry_t get_swap_page(
#endif /* CONFIG_SWAP */
#ifdef CONFIG_THP_SWAP
-extern int split_swap_cluster(swp_entry_t entry);
+extern int split_swap_cluster(swp_entry_t entry, bool force);
extern int split_swap_cluster_map(swp_entry_t entry);
#else
-static inline int split_swap_cluster(swp_entry_t entry)
+static inline int split_swap_cluster(swp_entry_t entry, bool force)
{
return 0;
}
diff -puN mm/huge_memory.c~mm-thp-swap-support-pmd-swap-mapping-in-split_swap_cluster mm/huge_memory.c
--- a/mm/huge_memory.c~mm-thp-swap-support-pmd-swap-mapping-in-split_swap_cluster
+++ a/mm/huge_memory.c
@@ -2503,6 +2503,17 @@ static void __split_huge_page(struct pag
unfreeze_page(head);
+ /*
+ * Split swap cluster before unlocking sub-pages. So all
+ * sub-pages will be kept locked from THP has been split to
+ * swap cluster is split.
+ */
+ if (PageSwapCache(head)) {
+ swp_entry_t entry = { .val = page_private(head) };
+
+ split_swap_cluster(entry, true);
+ }
+
for (i = 0; i < HPAGE_PMD_NR; i++) {
struct page *subpage = head + i;
if (subpage == page)
@@ -2729,12 +2740,7 @@ int split_huge_page_to_list(struct page
__dec_node_page_state(page, NR_SHMEM_THPS);
spin_unlock(&pgdata->split_queue_lock);
__split_huge_page(page, list, flags);
- if (PageSwapCache(head)) {
- swp_entry_t entry = { .val = page_private(head) };
-
- ret = split_swap_cluster(entry);
- } else
- ret = 0;
+ ret = 0;
} else {
if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
pr_alert("total_mapcount: %u, page_count(): %u\n",
diff -puN mm/swapfile.c~mm-thp-swap-support-pmd-swap-mapping-in-split_swap_cluster mm/swapfile.c
--- a/mm/swapfile.c~mm-thp-swap-support-pmd-swap-mapping-in-split_swap_cluster
+++ a/mm/swapfile.c
@@ -1410,21 +1410,6 @@ static void swapcache_free_cluster(swp_e
}
}
}
-
-int split_swap_cluster(swp_entry_t entry)
-{
- struct swap_info_struct *si;
- struct swap_cluster_info *ci;
- unsigned long offset = swp_offset(entry);
-
- si = _swap_info_get(entry);
- if (!si)
- return -EBUSY;
- ci = lock_cluster(si, offset);
- cluster_clear_huge(ci);
- unlock_cluster(ci);
- return 0;
-}
#else
static inline void swapcache_free_cluster(swp_entry_t entry)
{
@@ -4069,6 +4054,36 @@ out:
unlock_cluster(ci);
return 0;
}
+
+int split_swap_cluster(swp_entry_t entry, bool force)
+{
+ struct swap_info_struct *si;
+ struct swap_cluster_info *ci;
+ unsigned long offset = swp_offset(entry);
+ int ret = 0;
+
+ si = get_swap_device(entry);
+ if (!si)
+ return -EINVAL;
+ ci = lock_cluster(si, offset);
+ /* The swap cluster has been split by someone else */
+ if (!cluster_is_huge(ci))
+ goto out;
+ VM_BUG_ON(!is_cluster_offset(offset));
+ VM_BUG_ON(cluster_count(ci) < SWAPFILE_CLUSTER);
+ /* If not forced, don't split swap cluster has swap cache */
+ if (!force && si->swap_map[offset] & SWAP_HAS_CACHE) {
+ ret = -EEXIST;
+ goto out;
+ }
+ cluster_set_count(ci, SWAPFILE_CLUSTER);
+ cluster_clear_huge(ci);
+
+out:
+ unlock_cluster(ci);
+ put_swap_device(si);
+ return ret;
+}
#endif
static int __init swapfile_init(void)
_
Patches currently in -mm which might be from ying.huang@xxxxxxxxx are
mm-clear_huge_page-move-order-algorithm-into-a-separate-function.patch
mm-huge-page-copy-target-sub-page-last-when-copy-huge-page.patch
mm-hugetlbfs-rename-address-to-haddr-in-hugetlb_cow.patch
mm-hugetlbfs-pass-fault-address-to-cow-handler.patch
mm-swap-fix-race-between-swapoff-and-some-swap-operations.patch
mm-swap-fix-race-between-swapoff-and-some-swap-operations-v6.patch
mm-fix-race-between-swapoff-and-mincore.patch
mm-thp-swap-enable-pmd-swap-operations-for-config_thp_swap.patch
mm-thp-swap-make-config_thp_swap-depends-on-config_swap.patch
mm-thp-swap-support-pmd-swap-mapping-in-swap_duplicate.patch
mm-thp-swap-support-pmd-swap-mapping-in-swapcache_free_cluster.patch
mm-thp-swap-support-pmd-swap-mapping-in-free_swap_and_cache-swap_free.patch
mm-thp-swap-support-pmd-swap-mapping-when-splitting-huge-pmd.patch
mm-thp-swap-support-pmd-swap-mapping-in-split_swap_cluster.patch
mm-thp-swap-support-to-read-a-huge-swap-cluster-for-swapin-a-thp.patch
mm-thp-swap-swapin-a-thp-as-a-whole.patch
mm-thp-swap-support-to-count-thp-swapin-and-its-fallback.patch
mm-thp-swap-add-sysfs-interface-to-configure-thp-swapin.patch
mm-thp-swap-support-pmd-swap-mapping-in-swapoff.patch
mm-thp-swap-support-pmd-swap-mapping-in-madvise_free.patch
mm-cgroup-thp-swap-support-to-move-swap-account-for-pmd-swap-mapping.patch
mm-thp-swap-support-to-copy-pmd-swap-mapping-when-fork.patch
mm-thp-swap-free-pmd-swap-mapping-when-zap_huge_pmd.patch
mm-thp-swap-support-pmd-swap-mapping-for-madv_willneed.patch
mm-thp-swap-support-pmd-swap-mapping-in-mincore.patch
mm-thp-swap-support-pmd-swap-mapping-in-common-path.patch
mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp.patch
mm-thp-avoid-to-split-thp-when-reclaim-madv_free-thp.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
